Capacity management of Enterprise Applications (EAs) encompasses critical IT processes that maximize the IT system’s performance while minimizing operational costs. Effective management of EAs capacity can be enhanced through precise anomaly detection and workload forecasting. Given sufficient historical monitoring data of EAs, Machine Learning (ML) algorithms like Isolation Forest and XGBoost can be applied to address anomaly detection and forecasting tasks. However, the performance of these algorithms can strongly depend on the selected hyper-parameter values. Hence, Hyper-Parameter Optimization (HPO) is crucial for successfully adopting ML methods to solve real-world problems. The existing tuning methods like manual tuning, Grid Search, and Random Search often tend to be computationally expensive and time-consuming, making them ineffective for high-dimensional data. On the other hand, recent successes of Deep Reinforcement Learning (DRL) in handling various optimization problems have sparked interest in exploring its potential. Therefore, this work investigates the adaptation of DRL as a novel HPO approach. We present two implementation scenarios deployed in two real-world use cases and compare the results to the state-of-the-art tuning algorithms. The experiments indicate that the DRL algorithms can be adopted as tuning techniques since they demonstrate consistent policy learning and overall reward maximization.

Adaptive immune receptors, such as antibodies and T-cell receptors, recognize foreign threats with exquisite specificity. A major challenge in adaptive immunology is discovering the rules governing immune receptor-antigen binding in order to predict the antigen binding status of previously unseen immune receptors. Many studies assume that the antigen binding status of an immune receptor may be determined by the presence of a short motif in the complementarity determining region 3 (CDR3), disregarding other amino acids. To test this assumption, we present a method to discover short motifs which show high precision in predicting antigen binding and generalize well to unseen simulated and experimental data. Our analysis of a mutagenesis-based antibody dataset reveals 11 336 position-specific, mostly gapped motifs of 3-5 amino acids that retain high precision on independently generated experimental data. Using a subset of only 178 motifs, a simple classifier was made that on the independently generated dataset outperformed a deep learning model proposed specifically for such datasets. In conclusion, our findings support the notion that for some antibodies, antigen binding may be largely determined by a short CDR3 motif. As more experimental data emerge, our methodology could serve as a foundation for in-depth investigations into antigen binding signals.